EMBER2024 Classifiers

This repository includes 14 LightGBM classifiers trained on different malware analysis tasks, including malicious/benign file detection, malware family identification, and malware behavior prediction. These classifiers were trained and evaluated using the EMBER2024 dataset.

Paper about the classifiers: https://arxiv.org/pdf/2506.05074

GitHub repo for the EMBER2024 dataset: https://github.com/FutureComputing4AI/EMBER2024/

Citing

If you use EMBER2024 in your own research, please cite it using:

@inproceedings{joyce2025ember,
      title={EMBER2024 - A Benchmark Dataset for Holistic Evaluation of Malware Classifiers},
      author={Robert J. Joyce and Gideon Miller and Phil Roth and Richard Zak and Elliott Zaresky-Williams and Hyrum Anderson and Edward Raff and James Holt},
      year={2025},
      booktitle={Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
}